Agents

Works with the AI your team already uses.

Connect your AI agent to MCP Chats once. Your processes, data, emails and approvals are then ready in every conversation, with nothing new to learn.

Join the waitlist Find your agent

19 agents supported, each with a step-by-step setup.

Claude Desktop

Connected to MCP Chats

What processes can you see?

Ask Claude Desktop anything…

Illustrative conversation. Same setup in every agent.

Connected in three steps.

A few minutes, once. During the pilot we do it with you on a call.

Step 1
Create an access key
In MCP Chats, open Agents and create a key. You choose whether it can only run processes, or build them too.
Key for my agent
••••••••••••••••
Run processes
Step 2
Paste one block of settings
The Agents page fills in your address and key for you. Copy it into your agent’s settings.
```
"mcp-chats": {
  "url": "your address",
  "token": "your key"
}
```
Simplified. Each agent’s setup page shows its exact settings.
Step 3
Ask your agent
It lists the processes it can run for you, and you’re ready to hand over work.
What processes can you see?
Refund request, supplier onboarding and 1 more.

Find your agent.

Every setup is written from that agent’s own documentation.

Personal agents

AI assistants that work on your behalf.

Coding agents

Agents in the terminal, for technical teams.

Editors and desktop apps

Desktop apps and editors your team already has open.

Your own code

Build MCP Chats into your own software.

TypeScript SDK

Coming with the hosted pilot: Claude and ChatGPT, by signing in

Add MCP Chats in Claude or ChatGPT, sign in and choose what the agent may do. No key to copy. It’s built, and we switch it on once the hosted pilot is live.

It works for you, within the limits you set.

A connected agent acts as you, with the access you chose. You can revoke its key at any time.

It can

See the processes published for you
Start runs and do its steps
Use the data, systems and email templates you granted
Ask the right person to approve

It can’t

See your passwords or API keys
Change data through an action you haven’t enabled
Send emails you didn’t write, or to people you didn’t allow
Change Jev’s answers or the run’s record

These limits cover work routed through MCP Chats. Tools your agent has elsewhere are outside our control.

Then just ask.

Plain requests, in the chat you already use.

Design a process
“Design a process for onboarding a new supplier: collect their details, check them against our vendor list, and get finance to approve.”
Start a run
“Start supplier onboarding for Acme Ltd.”
Do agent steps
“Pick up any agent steps that are ready and do them.”
Check on runs
“Which runs are waiting on someone, and for what?”

Bring the routine you keep explaining.

Join the waitlist for our free pilot. When invited, we’ll help you turn one recurring job into a process and try it with your agent. For solo users and teams, with a setup call to get you started.

Join the waitlist